Mushroom: Reinforcement Learning python library.
Contents of this document:
Mushroom is a python Reinforcement Learning (RL) library whose modularity allows to easily use well known python libraries for tensor computation (e.g. PyTorch, Tensorflow) and RL benchmark (e.g. OpenAI Gym, PyBullet). It allows to perform RL experiments in a simple way providing online TD (e.g. Q-Learning, SARSA), batch TD (e.g. FQI) algorithms, deep RL algorithms (e.g. DQN and DDPG), and several policy-search algorithms (e.g. REINFORCE, REPS).
Full documentation available at http://mushroomrl.readthedocs.io/en/latest/.
You can do a minimal installation of
git clone https://github.com/carloderamo/mushroom.git cd mushroom pip3 install -e .
To install the whole set of features, you will need additional packages installed. You can install everything by running:
pip3 install -e '.[all]'
To run experiments, Mushroom requires a script file that provides the necessary information for the experiment. Follow the scripts in the "examples" folder to have an idea of how an experiment can be run.
For instance, to run a quick experiment with one of the provided example scripts, run: